#include "i915_trace.h"
#include "intel_drv.h"
+/*
+ * 965+ support PIPE_CONTROL commands, which provide finer grained control
+ * over cache flushing.
+ */
+struct pipe_control {
+ struct drm_i915_gem_object *obj;
+ volatile u32 *cpu_page;
+ u32 gtt_offset;
+};
+
static inline int ring_space(struct intel_ring_buffer *ring)
{
int space = (ring->head & HEAD_ADDR) - (ring->tail + 8);
return 0;
}
+/**
+ * Emits a PIPE_CONTROL with a non-zero post-sync operation, for
+ * implementing two workarounds on gen6. From section 1.4.7.1
+ * "PIPE_CONTROL" of the Sandy Bridge PRM volume 2 part 1:
+ *
+ * [DevSNB-C+{W/A}] Before any depth stall flush (including those
+ * produced by non-pipelined state commands), software needs to first
+ * send a PIPE_CONTROL with no bits set except Post-Sync Operation !=
+ * 0.
+ *
+ * [Dev-SNB{W/A}]: Before a PIPE_CONTROL with Write Cache Flush Enable
+ * =1, a PIPE_CONTROL with any non-zero post-sync-op is required.
+ *
+ * And the workaround for these two requires this workaround first:
+ *
+ * [Dev-SNB{W/A}]: Pipe-control with CS-stall bit set must be sent
+ * BEFORE the pipe-control with a post-sync op and no write-cache
+ * flushes.
+ *
+ * And this last workaround is tricky because of the requirements on
+ * that bit. From section 1.4.7.2.3 "Stall" of the Sandy Bridge PRM
+ * volume 2 part 1:
+ *
+ * "1 of the following must also be set:
+ * - Render Target Cache Flush Enable ([12] of DW1)
+ * - Depth Cache Flush Enable ([0] of DW1)
+ * - Stall at Pixel Scoreboard ([1] of DW1)
+ * - Depth Stall ([13] of DW1)
+ * - Post-Sync Operation ([13] of DW1)
+ * - Notify Enable ([8] of DW1)"
+ *
+ * The cache flushes require the workaround flush that triggered this
+ * one, so we can't use it. Depth stall would trigger the same.
+ * Post-sync nonzero is what triggered this second workaround, so we
+ * can't use that one either. Notify enable is IRQs, which aren't
+ * really our business. That leaves only stall at scoreboard.
+ */
+static int
+intel_emit_post_sync_nonzero_flush(struct intel_ring_buffer *ring)
+{
+ struct pipe_control *pc = ring->private;
+ u32 scratch_addr = pc->gtt_offset + 128;
+ int ret;
+
+
+ ret = intel_ring_begin(ring, 6);
+ if (ret)
+ return ret;
+
+ intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(5));
+ intel_ring_emit(ring, PIPE_CONTROL_CS_STALL |
+ PIPE_CONTROL_STALL_AT_SCOREBOARD);
+ intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT); /* address */
+ intel_ring_emit(ring, 0); /* low dword */
+ intel_ring_emit(ring, 0); /* high dword */
+ intel_ring_emit(ring, MI_NOOP);
+ intel_ring_advance(ring);
+
+ ret = intel_ring_begin(ring, 6);
+ if (ret)
+ return ret;
+
+ intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(5));
+ intel_ring_emit(ring, PIPE_CONTROL_QW_WRITE);
+ intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT); /* address */
+ intel_ring_emit(ring, 0);
+ intel_ring_emit(ring, 0);
+ intel_ring_emit(ring, MI_NOOP);
+ intel_ring_advance(ring);
+
+ return 0;
+}
+
+static int
+gen6_render_ring_flush(struct intel_ring_buffer *ring,
+ u32 invalidate_domains, u32 flush_domains)
+{
+ u32 flags = 0;
+ struct pipe_control *pc = ring->private;
+ u32 scratch_addr = pc->gtt_offset + 128;
+ int ret;
+
+ /* Force SNB workarounds for PIPE_CONTROL flushes */
+ intel_emit_post_sync_nonzero_flush(ring);
+
+ /* Just flush everything. Experiments have shown that reducing the
+ * number of bits based on the write domains has little performance
+ * impact.
+ */
+ flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
+ flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
+ flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
+ flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
+ flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
+ flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
+ flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+
+ ret = intel_ring_begin(ring, 6);
+ if (ret)
+ return ret;
+
+ intel_ring_emit(ring, GFX_OP_PIPE_CONTROL(5));
+ intel_ring_emit(ring, flags);
+ intel_ring_emit(ring, scratch_addr | PIPE_CONTROL_GLOBAL_GTT);
+ intel_ring_emit(ring, 0); /* lower dword */
+ intel_ring_emit(ring, 0); /* uppwer dword */
+ intel_ring_emit(ring, MI_NOOP);
+ intel_ring_advance(ring);
+
+ return 0;
+}
+
static void ring_write_tail(struct intel_ring_buffer *ring,
u32 value)
{
return 0;
}
-/*
- * 965+ support PIPE_CONTROL commands, which provide finer grained control
- * over cache flushing.
- */
-struct pipe_control {
- struct drm_i915_gem_object *obj;
- volatile u32 *cpu_page;
- u32 gtt_offset;
-};
-
static int
init_pipe_control(struct intel_ring_buffer *ring)
{
GFX_MODE_ENABLE(GFX_REPLAY_MODE));
}
- if (INTEL_INFO(dev)->gen >= 6) {
- } else if (IS_GEN5(dev)) {
+ if (INTEL_INFO(dev)->gen >= 5) {
ret = init_pipe_control(ring);
if (ret)
return ret;
}
static u32
+gen6_ring_get_seqno(struct intel_ring_buffer *ring)
+{
+ struct drm_device *dev = ring->dev;
+
+ /* Workaround to force correct ordering between irq and seqno writes on
+ * ivb (and maybe also on snb) by reading from a CS register (like
+ * ACTHD) before reading the status page. */
+ if (IS_GEN7(dev))
+ intel_ring_get_active_head(ring);
+ return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
+}
+
+static u32
ring_get_seqno(struct intel_ring_buffer *ring)
{
return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
if (!dev->irq_enabled)
return false;
+ /* It looks like we need to prevent the gt from suspending while waiting
+ * for an notifiy irq, otherwise irqs seem to get lost on at least the
+ * blt/bsd rings on ivb. */
+ if (IS_GEN7(dev))
+ gen6_gt_force_wake_get(dev_priv);
+
spin_lock(&ring->irq_lock);
if (ring->irq_refcount++ == 0) {
ring->irq_mask &= ~rflag;
ironlake_disable_irq(dev_priv, gflag);
}
spin_unlock(&ring->irq_lock);
+
+ if (IS_GEN7(dev))
+ gen6_gt_force_wake_put(dev_priv);
}
static bool
* of the buffer.
*/
ring->effective_size = ring->size;
- if (IS_I830(ring->dev))
+ if (IS_I830(ring->dev) || IS_845G(ring->dev))
ring->effective_size -= 128;
return 0;
.write_tail = gen6_bsd_ring_write_tail,
.flush = gen6_ring_flush,
.add_request = gen6_add_request,
- .get_seqno = ring_get_seqno,
+ .get_seqno = gen6_ring_get_seqno,
.irq_get = gen6_bsd_ring_get_irq,
.irq_put = gen6_bsd_ring_put_irq,
.dispatch_execbuffer = gen6_ring_dispatch_execbuffer,
.write_tail = ring_write_tail,
.flush = blt_ring_flush,
.add_request = gen6_add_request,
- .get_seqno = ring_get_seqno,
+ .get_seqno = gen6_ring_get_seqno,
.irq_get = blt_ring_get_irq,
.irq_put = blt_ring_put_irq,
.dispatch_execbuffer = gen6_ring_dispatch_execbuffer,
*ring = render_ring;
if (INTEL_INFO(dev)->gen >= 6) {
ring->add_request = gen6_add_request;
+ ring->flush = gen6_render_ring_flush;
ring->irq_get = gen6_render_ring_get_irq;
ring->irq_put = gen6_render_ring_put_irq;
+ ring->get_seqno = gen6_ring_get_seqno;
} else if (IS_GEN5(dev)) {
ring->add_request = pc_render_add_request;
ring->get_seqno = pc_render_get_seqno;
projects / linux-flexiantxendom0.git / blobdiff